{"as_of":"2026-08-13T12:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:57d25873d1d1ba93c0a5bec5d30e226de82fc9eb6075c96cc95a34b6ec747f2a","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T10:48:41.378646Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-12T10:48:45.114893Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1807.01830","last_updated":"2018-07-05T02:34:40Z","snapshot_observed_at":"2026-07-06T06:48:29.164157Z","submitted_at":"2018-07-05T02:34:40Z","title":"Per-decision Multi-step Temporal Difference Learning with Control Variates","version":1},"cited_work":{"arxiv_id":"1807.01830","doi":null,"metadata_source":"pith","pith_arxiv_id":"1807.01830","snapshot_observed_at":"2026-08-12T10:48:45.114893Z","title":"Per-decision Multi-step Temporal Difference Learning with Control Variates","venue":"cs.LG","work_id":"a79b32cd-7a51-4585-8c43-22401f266a3c","year":2018},"citing_paper":{"arxiv_id":"2411.18892","last_updated":"2025-02-01T23:49:26Z","snapshot_observed_at":"2026-08-13T05:19:39.475481Z","submitted_at":"2024-11-28T03:53:14Z","title":"A Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-12T10:48:41.378646Z"},"links":{"cited_paper":"/paper/1807.01830","citing_paper":"/paper/2411.18892"},"observation_digest":"sha256:22795302f617a9f3170ec96091727c1712e4cda69dc65db2b7b21e6c7db1843a","observation_id":"f29e2377-b74d-49d2-a97f-f4a5550e59f0","resolution":{"observed_at":"2026-08-12T10:48:45.171220Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/1807.01830/citation-record","integrity":"/paper/1807.01830/integrity","json":"/paper/1807.01830/citation-record.json","paper":"/paper/1807.01830"},"outbound":[],"paper":{"arxiv_id":"1807.01830","last_updated":"2018-07-05T02:34:40Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T06:48:29.164157Z","submitted_at":"2018-07-05T02:34:40Z","title":"Per-decision Multi-step Temporal Difference Learning with Control Variates"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:1807.01830."}